© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6104
    Prev
    Next
    INDEX
    Explanations

    .out

    np_max-act · gemini-2.0-flash

    The neuron fires on Java console‐printing calls—specifically occurrences of “System.out” (e.g. System.out.println).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pop
    -0.07
     مهم
    -0.07
    き
    -0.07
    stead
    -0.07
    cr
    -0.07
     암
    -0.06
    circle
    -0.06
     fermented
    -0.06
    cheduler
    -0.06
     capac
    -0.06
    POSITIVE LOGITS
    .out
    0.11
    *out
    0.07
     Neu
    0.07
    �
    0.07
     DataView
    0.07
     Might
    0.07
    apeut
    0.07
     SWAT
    0.07
     Suppose
    0.07
    orgt
    0.07
    Activations Density 0.003%

    No Known Activations